Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite the annotations already carrying destructive/openWorld flags, the description adds genuinely useful behavioral detail: it discloses that the heuristic does not inspect file contents, verify duplicate content, move or delete files, or perform the cleanup implied by its receipt identifier, and it states that product credentials, signed mandates, and single-use grants are required and that non-JSON/unavailable backends surface as tool errors. The only blemish is tension with destructiveHint=true, since the description insists it never moves or deletes files, though it does frame destructive actions as requiring outside approval.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is bloated and repetitive, with two overlapping purpose statements (one denying capabilities the other asserts), plus long boilerplate about authority, credentials, and proxy status. It is not front-loaded on what the tool does, and the most decision-relevant fact (sandbox filename heuristic) is buried behind 'Unavailable historical backend.'

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive-flagged, open-world, no-output-schema tool the description does cover backend availability, error behavior, and authority prerequisites reasonably well. It is incomplete on the input contract (the opaque mode parameter) and on how its claimed capabilities reconcile with its disclaimed ones, so an agent still cannot confidently invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single free-form 'mode' property (maxProperties 64, additionalProperties true) is essentially undocumented. The description says only that signed mandates or grants 'remain required' and never explains what mode values or arguments the POST body expects, leaving the agent without enough to construct a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description does state a concrete mechanism (classifying supplied filenames via invoice/contract substrings and flagging names containing 'copy') and a deliverable (a cleanup review queue). However, it opens by declaring itself an 'Unavailable historical backend,' and the second paragraph claims broader capabilities ('extract document metadata, detect duplicates') that the first paragraph explicitly disclaims, so the actual purpose is muddled rather than crisp. It does not differentiate itself from the many sibling rail tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It notes this is a sandbox/demo and a 'catalog proxy entry, not a guarantee of backend availability,' which is weak negative guidance. There is an 'Operating boundary' line saying destructive moves/deletions require outside approval, but no statement of when to choose this tool over the 20+ sibling tools or what preconditions must hold before invoking it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.